GraphGAN: Graph Representation Learning with Generative Adversarial Nets

22 Nov 2017 β€’ Hongwei Wang β€’ Jia Wang β€’ Jialin Wang β€’ Miao Zhao β€’ Wei-Nan Zhang β€’ Fuzheng Zhang β€’ Xing Xie β€’ Minyi Guo

The goal of graph representation learning is to embed each vertex in a graph into a low-dimensional vector space. Existing graph representation learning methods can be classified into two categories: generative models that learn the underlying connectivity distribution in the graph, and discriminative models that predict the probability of edge existence between a pair of vertices... (read more)

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Node Classification BlogCatalog GraphGAN Accuracy 23.20% # 2
Macro-F1 0.221 # 2
Node Classification Wikipedia GraphGAN Accuracy 21.30% # 1
Macro-F1 0.194 # 1

Methods used in the Paper


METHOD TYPE
Softmax
Output Functions